© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 13-LLAMASCOPE-RES-32K
    6. 730
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions among characters in social situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rea
    -0.15
    ãģĴ
    -0.15
    cmp
    -0.14
    NSS
    -0.14
    uj
    -0.14
    aut
    -0.14
    uci
    -0.14
    еÑĢж
    -0.14
     Reyes
    -0.13
    ila
    -0.13
    POSITIVE LOGITS
     instead
    0.23
    instead
    0.21
     rather
    0.20
     alone
    0.19
    alone
    0.19
    rather
    0.18
     Instead
    0.18
     Ital
    0.18
     Alone
    0.17
     Rather
    0.16
    Activations Density 0.232%

    No Known Activations